# Marked Temporal Dynamics Modeling based on Recurrent Neural Network

## TL;DR

This paper introduces a recurrent neural network-based approach for modeling marked temporal dynamics, enabling simultaneous prediction of event timing and type by capturing their dependency, and demonstrates superior performance over existing methods.

## Contribution

The paper proposes a mark-specific intensity function within a recurrent neural network to jointly predict event time and mark, addressing their dependency in marked temporal dynamics.

## Key findings

- Outperforms state-of-the-art methods in prediction accuracy
- Effectively models dependency between event time and mark
- Validated on two real-world datasets

## Abstract

We are now witnessing the increasing availability of event stream data, i.e., a sequence of events with each event typically being denoted by the time it occurs and its mark information (e.g., event type). A fundamental problem is to model and predict such kind of marked temporal dynamics, i.e., when the next event will take place and what its mark will be. Existing methods either predict only the mark or the time of the next event, or predict both of them, yet separately. Indeed, in marked temporal dynamics, the time and the mark of the next event are highly dependent on each other, requiring a method that could simultaneously predict both of them. To tackle this problem, in this paper, we propose to model marked temporal dynamics by using a mark-specific intensity function to explicitly capture the dependency between the mark and the time of the next event. Extensive experiments on two datasets demonstrate that the proposed method outperforms state-of-the-art methods at predicting marked temporal dynamics.